Search

Objective: The 19‐item Epilepsy Surgery Satisfaction Questionnaire (ESSQ‐19) is a validated and reliable post hoc means of assessing patient satisfaction with epilepsy surgery. Prediction models building on these data can be used to counsel patients. Methods: The ESSQ‐19 was derived and validated on 229 patients recruited from Canada and Sweden. We isolated 201 (88%) patients with complete clinical data for this analysis. These patients were adults (≥18 years old) who underwent epilepsy surgery 1 year or more prior to answering the questionnaire. We extracted each patient's ESSQ‐19 score (scale is 0–100; 100 represents complete satisfaction) and relevant clinical variables that were standardized prior to the analysis. We used machine learning (linear kernel support vector regression [SVR]) to predict satisfaction and assessed performance using the R2 calculated following threefold cross‐validation. Model parameters were ranked to infer the importance of each clinical variable to overall satisfaction with epilepsy surgery. Results: Median age was 41 years (interquartile range [IQR] = 32–53), and 116 (57%) were female. Median ESSQ‐19 global score was 68 (IQR = 59–75), and median time from surgery was 5.4 years (IQR = 2.0–8.9). Linear kernel SVR performed well following threefold cross‐validation, with an R2 of.44 (95% confidence interval =.36–.52). Increasing satisfaction was associated with postoperative self‐perceived quality of life, seizure freedom, and reductions in antiseizure medications. Self‐perceived epilepsy disability, age, and increasing frequency of seizures that impair awareness were associated with reduced satisfaction. Significance: Machine learning applied postoperatively to the ESSQ‐19 can be used to predict surgical satisfaction. This algorithm, once externally validated, can be used in clinical settings by fixing immutable clinical characteristics and adjusting hypothesized postoperative variables, to counsel patients at an individual level on how satisfied they will be with differing surgical outcomes. [ABSTRACT FROM AUTHOR]

Objective: To use clinically informed machine learning to derive prediction models for early and late premature death in epilepsy. Methods: This was a population‐based primary care observational cohort study. All patients meeting a case definition for incident epilepsy in the Health Improvement Network database for inclusive years 2000‐2012 were included. A modified Delphi process identified 30 potential risk factors. Outcome was early (within 4 years of epilepsy diagnosis) and late (4 years or more from diagnosis) mortality. We used regularized logistic regression, support vector machines, Gaussian naive Bayes, and random forest classifiers to predict outcomes. We assessed model calibration, discrimination, and generalizability using the Brier score, mean area under the receiver operating characteristic curve (AUC) derived from stratified fivefold cross‐validation, plotted calibration curves, and extracted measures of association where possible. Results: We identified 10 499 presumed incident cases from 11 194 182 patients. All models performed comparably well following stratified fivefold cross‐validation, with AUCs ranging from 0.73 to 0.81 and from 0.71 to 0.79 for early and late death, respectively. In addition to comorbid disease, social habits (alcoholism odds ratio [OR] for early death = 1.54, 95% confidence interval [CI] = 1.12‐2.11 and OR for late death = 2.62, 95% CI = 1.66‐4.16) and treatment patterns (OR for early death when no antiseizure medication [ASM] was prescribed at baseline = 1.33, 95% CI = 1.07‐1.64 and OR for late death after receipt of enzyme‐inducing ASM at baseline = 1.32, 95% CI = 1.04‐1.66) were significantly associated with increased risk of premature death. Baseline ASM polytherapy (OR = 0.55, 95% CI = 0.36‐0.85) was associated with reduced risk of early death. Significance: Clinically informed models using routine electronic medical records can be used to predict early and late mortality in epilepsy, with moderate to high accuracy and evidence of generalizability. Medical, social, and treatment‐related risk factors, such as delayed ASM prescription and baseline prescription of enzyme‐inducing ASMs, were important predictors. [ABSTRACT FROM AUTHOR]

Objective: To apply unsupervised machine learning to patient‐reported outcomes to identify clusters of epilepsy patients exhibiting unique psychosocial characteristics. Methods: Consecutive outpatients seen at the Calgary Comprehensive Epilepsy Program outpatient clinics with complete patient‐reported outcome measures on quality of life, health state valuation, depression, and epilepsy severity and disability were studied. Data were acquired at each patient's first clinic visit. We used k‐means++ to segregate the population into three unique clusters. We then used multinomial regression to determine factors that were statistically associated with patient assignment to each cluster. Results: We identified 462 consecutive patients with complete patient‐reported outcome measure (PROM) data. Post hoc analysis of each cluster revealed one reporting elevated measures of psychosocial health on all five PROMs ("high psychosocial health" cluster), one with intermediate measures ("intermediate" cluster), and one with poor overall measures of psychosocial health ("poor psychosocial health" cluster). Failing to achieve at least 1 year of seizure freedom (relative risk [RR] = 4.34, 95% confidence interval [CI] = 2.13‐9.09) predicted placement in the "intermediate" cluster relative to the "high" cluster. In addition, failing to achieve seizure freedom, social determinants of health, including the need for partially or completely subsidized income support (RR = 6.10, 95% CI = 2.79‐13.31, P <.001) and inability to drive (RR = 4.03, 95% CI = 1.6‐10.00, P =.003), and a history of a psychiatric disorder (RR = 3.16, 95% CI = 1.46‐6.85, P =.003) were associated with the "poor" cluster relative to the "high" cluster. Significance: Seizure‐related factors appear to drive placement in the "intermediate" cluster, with social determinants driving placement in the "poor" cluster, suggesting a threshold effect. Precision intervention based on cluster assignment, with an initial emphasis on improving social support and careful titration of medications for those reporting the worst psychosocial health, could help optimize health for patients with epilepsy. [ABSTRACT FROM AUTHOR]